Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a299bb8aa61119fd98c1c5f9ab42a23925f5cf60ec039ea7e37c8b6f58ab76
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df095c022ee12f8ea416f08fd0b86f25bb8ffbb0559692eb0675a32c3488f8a5
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17312a30c45f3e4662f8e435bd400ffe178ed482257955e1c7252bf6b58bf8c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d531c25034f626df24a202eb6f7161b884321c584c9b6d6cdeb2e78c1a2d10a4
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,164 @@
+{"current_steps": 1, "total_steps": 468, "loss": 0.8883, "lr": 4.2553191489361704e-07, "epoch": 0.006389776357827476, "percentage": 0.21, "elapsed_time": "0:00:29", "remaining_time": "3:48:36"}
+{"current_steps": 2, "total_steps": 468, "loss": 0.8365, "lr": 8.510638297872341e-07, "epoch": 0.012779552715654952, "percentage": 0.43, "elapsed_time": "0:00:52", "remaining_time": "3:24:59"}
+{"current_steps": 3, "total_steps": 468, "loss": 0.8863, "lr": 1.276595744680851e-06, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:14", "remaining_time": "3:13:09"}
+{"current_steps": 4, "total_steps": 468, "loss": 0.8793, "lr": 1.7021276595744682e-06, "epoch": 0.025559105431309903, "percentage": 0.85, "elapsed_time": "0:01:36", "remaining_time": "3:06:31"}
+{"current_steps": 5, "total_steps": 468, "loss": 0.8246, "lr": 2.1276595744680853e-06, "epoch": 0.03194888178913738, "percentage": 1.07, "elapsed_time": "0:01:59", "remaining_time": "3:04:25"}
+{"current_steps": 6, "total_steps": 468, "loss": 0.8488, "lr": 2.553191489361702e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:23", "remaining_time": "3:03:37"}
+{"current_steps": 7, "total_steps": 468, "loss": 0.815, "lr": 2.978723404255319e-06, "epoch": 0.04472843450479233, "percentage": 1.5, "elapsed_time": "0:02:39", "remaining_time": "2:55:09"}
+{"current_steps": 8, "total_steps": 468, "loss": 0.7566, "lr": 3.4042553191489363e-06, "epoch": 0.051118210862619806, "percentage": 1.71, "elapsed_time": "0:02:59", "remaining_time": "2:52:03"}
+{"current_steps": 9, "total_steps": 468, "loss": 0.7551, "lr": 3.8297872340425535e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:22", "remaining_time": "2:52:22"}
+{"current_steps": 10, "total_steps": 468, "loss": 0.7457, "lr": 4.255319148936171e-06, "epoch": 0.06389776357827476, "percentage": 2.14, "elapsed_time": "0:03:44", "remaining_time": "2:51:27"}
+{"current_steps": 11, "total_steps": 468, "loss": 0.6988, "lr": 4.680851063829788e-06, "epoch": 0.07028753993610223, "percentage": 2.35, "elapsed_time": "0:04:05", "remaining_time": "2:49:42"}
+{"current_steps": 12, "total_steps": 468, "loss": 0.8105, "lr": 5.106382978723404e-06, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:24", "remaining_time": "2:47:37"}
+{"current_steps": 13, "total_steps": 468, "loss": 0.7639, "lr": 5.531914893617022e-06, "epoch": 0.08306709265175719, "percentage": 2.78, "elapsed_time": "0:04:46", "remaining_time": "2:47:20"}
+{"current_steps": 14, "total_steps": 468, "loss": 0.7143, "lr": 5.957446808510638e-06, "epoch": 0.08945686900958466, "percentage": 2.99, "elapsed_time": "0:05:10", "remaining_time": "2:47:39"}
+{"current_steps": 15, "total_steps": 468, "loss": 0.7494, "lr": 6.382978723404256e-06, "epoch": 0.09584664536741214, "percentage": 3.21, "elapsed_time": "0:05:29", "remaining_time": "2:45:37"}
+{"current_steps": 16, "total_steps": 468, "loss": 0.7079, "lr": 6.808510638297873e-06, "epoch": 0.10223642172523961, "percentage": 3.42, "elapsed_time": "0:05:51", "remaining_time": "2:45:29"}
+{"current_steps": 17, "total_steps": 468, "loss": 0.6638, "lr": 7.234042553191491e-06, "epoch": 0.10862619808306709, "percentage": 3.63, "elapsed_time": "0:06:12", "remaining_time": "2:44:30"}
+{"current_steps": 18, "total_steps": 468, "loss": 0.6562, "lr": 7.659574468085107e-06, "epoch": 0.11501597444089456, "percentage": 3.85, "elapsed_time": "0:06:35", "remaining_time": "2:44:45"}
+{"current_steps": 19, "total_steps": 468, "loss": 0.6753, "lr": 8.085106382978723e-06, "epoch": 0.12140575079872204, "percentage": 4.06, "elapsed_time": "0:06:57", "remaining_time": "2:44:33"}
+{"current_steps": 20, "total_steps": 468, "loss": 0.6064, "lr": 8.510638297872341e-06, "epoch": 0.12779552715654952, "percentage": 4.27, "elapsed_time": "0:07:20", "remaining_time": "2:44:34"}
+{"current_steps": 21, "total_steps": 468, "loss": 0.6292, "lr": 8.936170212765958e-06, "epoch": 0.134185303514377, "percentage": 4.49, "elapsed_time": "0:07:42", "remaining_time": "2:43:56"}
+{"current_steps": 22, "total_steps": 468, "loss": 0.6444, "lr": 9.361702127659576e-06, "epoch": 0.14057507987220447, "percentage": 4.7, "elapsed_time": "0:08:02", "remaining_time": "2:42:58"}
+{"current_steps": 23, "total_steps": 468, "loss": 0.641, "lr": 9.787234042553192e-06, "epoch": 0.14696485623003194, "percentage": 4.91, "elapsed_time": "0:08:22", "remaining_time": "2:42:06"}
+{"current_steps": 24, "total_steps": 468, "loss": 0.6496, "lr": 1.0212765957446808e-05, "epoch": 0.15335463258785942, "percentage": 5.13, "elapsed_time": "0:08:41", "remaining_time": "2:40:51"}
+{"current_steps": 25, "total_steps": 468, "loss": 0.6305, "lr": 1.0638297872340426e-05, "epoch": 0.1597444089456869, "percentage": 5.34, "elapsed_time": "0:09:03", "remaining_time": "2:40:24"}
+{"current_steps": 26, "total_steps": 468, "loss": 0.6414, "lr": 1.1063829787234044e-05, "epoch": 0.16613418530351437, "percentage": 5.56, "elapsed_time": "0:09:24", "remaining_time": "2:39:57"}
+{"current_steps": 27, "total_steps": 468, "loss": 0.5928, "lr": 1.1489361702127662e-05, "epoch": 0.17252396166134185, "percentage": 5.77, "elapsed_time": "0:09:43", "remaining_time": "2:38:50"}
+{"current_steps": 28, "total_steps": 468, "loss": 0.5898, "lr": 1.1914893617021277e-05, "epoch": 0.17891373801916932, "percentage": 5.98, "elapsed_time": "0:10:01", "remaining_time": "2:37:29"}
+{"current_steps": 29, "total_steps": 468, "loss": 0.5896, "lr": 1.2340425531914895e-05, "epoch": 0.1853035143769968, "percentage": 6.2, "elapsed_time": "0:10:22", "remaining_time": "2:36:56"}
+{"current_steps": 30, "total_steps": 468, "loss": 0.5853, "lr": 1.2765957446808513e-05, "epoch": 0.19169329073482427, "percentage": 6.41, "elapsed_time": "0:10:41", "remaining_time": "2:36:00"}
+{"current_steps": 31, "total_steps": 468, "loss": 0.5758, "lr": 1.3191489361702127e-05, "epoch": 0.19808306709265175, "percentage": 6.62, "elapsed_time": "0:11:00", "remaining_time": "2:35:10"}
+{"current_steps": 32, "total_steps": 468, "loss": 0.585, "lr": 1.3617021276595745e-05, "epoch": 0.20447284345047922, "percentage": 6.84, "elapsed_time": "0:11:18", "remaining_time": "2:34:01"}
+{"current_steps": 33, "total_steps": 468, "loss": 0.584, "lr": 1.4042553191489363e-05, "epoch": 0.2108626198083067, "percentage": 7.05, "elapsed_time": "0:11:37", "remaining_time": "2:33:15"}
+{"current_steps": 34, "total_steps": 468, "loss": 0.553, "lr": 1.4468085106382981e-05, "epoch": 0.21725239616613418, "percentage": 7.26, "elapsed_time": "0:11:55", "remaining_time": "2:32:14"}
+{"current_steps": 35, "total_steps": 468, "loss": 0.6051, "lr": 1.4893617021276596e-05, "epoch": 0.22364217252396165, "percentage": 7.48, "elapsed_time": "0:12:20", "remaining_time": "2:32:36"}
+{"current_steps": 36, "total_steps": 468, "loss": 0.5398, "lr": 1.5319148936170214e-05, "epoch": 0.23003194888178913, "percentage": 7.69, "elapsed_time": "0:12:40", "remaining_time": "2:32:04"}
+{"current_steps": 37, "total_steps": 468, "loss": 0.5542, "lr": 1.5744680851063832e-05, "epoch": 0.2364217252396166, "percentage": 7.91, "elapsed_time": "0:13:02", "remaining_time": "2:31:51"}
+{"current_steps": 38, "total_steps": 468, "loss": 0.5516, "lr": 1.6170212765957446e-05, "epoch": 0.24281150159744408, "percentage": 8.12, "elapsed_time": "0:13:24", "remaining_time": "2:31:40"}
+{"current_steps": 39, "total_steps": 468, "loss": 0.5335, "lr": 1.6595744680851064e-05, "epoch": 0.24920127795527156, "percentage": 8.33, "elapsed_time": "0:13:44", "remaining_time": "2:31:08"}
+{"current_steps": 40, "total_steps": 468, "loss": 0.5412, "lr": 1.7021276595744682e-05, "epoch": 0.25559105431309903, "percentage": 8.55, "elapsed_time": "0:14:04", "remaining_time": "2:30:35"}
+{"current_steps": 41, "total_steps": 468, "loss": 0.5559, "lr": 1.74468085106383e-05, "epoch": 0.26198083067092653, "percentage": 8.76, "elapsed_time": "0:14:22", "remaining_time": "2:29:42"}
+{"current_steps": 42, "total_steps": 468, "loss": 0.5111, "lr": 1.7872340425531915e-05, "epoch": 0.268370607028754, "percentage": 8.97, "elapsed_time": "0:14:40", "remaining_time": "2:28:48"}
+{"current_steps": 43, "total_steps": 468, "loss": 0.5683, "lr": 1.8297872340425533e-05, "epoch": 0.2747603833865815, "percentage": 9.19, "elapsed_time": "0:15:00", "remaining_time": "2:28:19"}
+{"current_steps": 44, "total_steps": 468, "loss": 0.5768, "lr": 1.872340425531915e-05, "epoch": 0.28115015974440893, "percentage": 9.4, "elapsed_time": "0:15:24", "remaining_time": "2:28:27"}
+{"current_steps": 45, "total_steps": 468, "loss": 0.5249, "lr": 1.914893617021277e-05, "epoch": 0.28753993610223644, "percentage": 9.62, "elapsed_time": "0:15:47", "remaining_time": "2:28:30"}
+{"current_steps": 46, "total_steps": 468, "loss": 0.5358, "lr": 1.9574468085106384e-05, "epoch": 0.2939297124600639, "percentage": 9.83, "elapsed_time": "0:16:09", "remaining_time": "2:28:14"}
+{"current_steps": 47, "total_steps": 468, "loss": 0.5599, "lr": 2e-05, "epoch": 0.3003194888178914, "percentage": 10.04, "elapsed_time": "0:16:33", "remaining_time": "2:28:21"}
+{"current_steps": 48, "total_steps": 468, "loss": 0.5428, "lr": 1.9999721578003894e-05, "epoch": 0.30670926517571884, "percentage": 10.26, "elapsed_time": "0:16:56", "remaining_time": "2:28:18"}
+{"current_steps": 49, "total_steps": 468, "loss": 0.5518, "lr": 1.9998886327519337e-05, "epoch": 0.31309904153354634, "percentage": 10.47, "elapsed_time": "0:17:13", "remaining_time": "2:27:13"}
+{"current_steps": 50, "total_steps": 468, "loss": 0.5467, "lr": 1.999749429505675e-05, "epoch": 0.3194888178913738, "percentage": 10.68, "elapsed_time": "0:17:33", "remaining_time": "2:26:48"}
+{"current_steps": 51, "total_steps": 468, "loss": 0.5481, "lr": 1.9995545558130624e-05, "epoch": 0.3258785942492013, "percentage": 10.9, "elapsed_time": "0:17:53", "remaining_time": "2:26:21"}
+{"current_steps": 52, "total_steps": 468, "loss": 0.5402, "lr": 1.9993040225255205e-05, "epoch": 0.33226837060702874, "percentage": 11.11, "elapsed_time": "0:18:19", "remaining_time": "2:26:33"}
+{"current_steps": 53, "total_steps": 468, "loss": 0.5053, "lr": 1.998997843593845e-05, "epoch": 0.33865814696485624, "percentage": 11.32, "elapsed_time": "0:18:38", "remaining_time": "2:25:59"}
+{"current_steps": 54, "total_steps": 468, "loss": 0.5555, "lr": 1.9986360360674252e-05, "epoch": 0.3450479233226837, "percentage": 11.54, "elapsed_time": "0:18:58", "remaining_time": "2:25:25"}
+{"current_steps": 55, "total_steps": 468, "loss": 0.5352, "lr": 1.9982186200932964e-05, "epoch": 0.3514376996805112, "percentage": 11.75, "elapsed_time": "0:19:19", "remaining_time": "2:25:10"}
+{"current_steps": 56, "total_steps": 468, "loss": 0.5788, "lr": 1.9977456189150164e-05, "epoch": 0.35782747603833864, "percentage": 11.97, "elapsed_time": "0:19:38", "remaining_time": "2:24:29"}
+{"current_steps": 57, "total_steps": 468, "loss": 0.5835, "lr": 1.9972170588713715e-05, "epoch": 0.36421725239616615, "percentage": 12.18, "elapsed_time": "0:20:01", "remaining_time": "2:24:23"}
+{"current_steps": 58, "total_steps": 468, "loss": 0.4919, "lr": 1.9966329693949098e-05, "epoch": 0.3706070287539936, "percentage": 12.39, "elapsed_time": "0:20:24", "remaining_time": "2:24:18"}
+{"current_steps": 59, "total_steps": 468, "loss": 0.5141, "lr": 1.9959933830103034e-05, "epoch": 0.3769968051118211, "percentage": 12.61, "elapsed_time": "0:20:44", "remaining_time": "2:23:49"}
+{"current_steps": 60, "total_steps": 468, "loss": 0.5191, "lr": 1.9952983353325358e-05, "epoch": 0.38338658146964855, "percentage": 12.82, "elapsed_time": "0:21:06", "remaining_time": "2:23:35"}
+{"current_steps": 61, "total_steps": 468, "loss": 0.5394, "lr": 1.9945478650649192e-05, "epoch": 0.38977635782747605, "percentage": 13.03, "elapsed_time": "0:21:29", "remaining_time": "2:23:26"}
+{"current_steps": 62, "total_steps": 468, "loss": 0.5427, "lr": 1.9937420139969397e-05, "epoch": 0.3961661341853035, "percentage": 13.25, "elapsed_time": "0:21:51", "remaining_time": "2:23:07"}
+{"current_steps": 63, "total_steps": 468, "loss": 0.5827, "lr": 1.9928808270019297e-05, "epoch": 0.402555910543131, "percentage": 13.46, "elapsed_time": "0:22:16", "remaining_time": "2:23:09"}
+{"current_steps": 64, "total_steps": 468, "loss": 0.5344, "lr": 1.9919643520345698e-05, "epoch": 0.40894568690095845, "percentage": 13.68, "elapsed_time": "0:22:38", "remaining_time": "2:22:52"}
+{"current_steps": 65, "total_steps": 468, "loss": 0.5622, "lr": 1.990992640128218e-05, "epoch": 0.41533546325878595, "percentage": 13.89, "elapsed_time": "0:22:59", "remaining_time": "2:22:35"}
+{"current_steps": 66, "total_steps": 468, "loss": 0.5313, "lr": 1.989965745392068e-05, "epoch": 0.4217252396166134, "percentage": 14.1, "elapsed_time": "0:23:20", "remaining_time": "2:22:08"}
+{"current_steps": 67, "total_steps": 468, "loss": 0.5455, "lr": 1.988883725008136e-05, "epoch": 0.4281150159744409, "percentage": 14.32, "elapsed_time": "0:23:40", "remaining_time": "2:21:43"}
+{"current_steps": 68, "total_steps": 468, "loss": 0.5426, "lr": 1.9877466392280773e-05, "epoch": 0.43450479233226835, "percentage": 14.53, "elapsed_time": "0:24:02", "remaining_time": "2:21:27"}
+{"current_steps": 69, "total_steps": 468, "loss": 0.5412, "lr": 1.9865545513698304e-05, "epoch": 0.44089456869009586, "percentage": 14.74, "elapsed_time": "0:24:21", "remaining_time": "2:20:53"}
+{"current_steps": 70, "total_steps": 468, "loss": 0.552, "lr": 1.9853075278140913e-05, "epoch": 0.4472843450479233, "percentage": 14.96, "elapsed_time": "0:24:42", "remaining_time": "2:20:31"}
+{"current_steps": 71, "total_steps": 468, "loss": 0.5703, "lr": 1.984005638000618e-05, "epoch": 0.4536741214057508, "percentage": 15.17, "elapsed_time": "0:25:05", "remaining_time": "2:20:20"}
+{"current_steps": 72, "total_steps": 468, "loss": 0.5481, "lr": 1.9826489544243623e-05, "epoch": 0.46006389776357826, "percentage": 15.38, "elapsed_time": "0:25:26", "remaining_time": "2:19:54"}
+{"current_steps": 73, "total_steps": 468, "loss": 0.5388, "lr": 1.981237552631434e-05, "epoch": 0.46645367412140576, "percentage": 15.6, "elapsed_time": "0:25:49", "remaining_time": "2:19:46"}
+{"current_steps": 74, "total_steps": 468, "loss": 0.5545, "lr": 1.9797715112148937e-05, "epoch": 0.4728434504792332, "percentage": 15.81, "elapsed_time": "0:26:10", "remaining_time": "2:19:23"}
+{"current_steps": 75, "total_steps": 468, "loss": 0.5306, "lr": 1.9782509118103773e-05, "epoch": 0.4792332268370607, "percentage": 16.03, "elapsed_time": "0:26:32", "remaining_time": "2:19:03"}
+{"current_steps": 76, "total_steps": 468, "loss": 0.5429, "lr": 1.9766758390915494e-05, "epoch": 0.48562300319488816, "percentage": 16.24, "elapsed_time": "0:26:52", "remaining_time": "2:18:34"}
+{"current_steps": 77, "total_steps": 468, "loss": 0.5188, "lr": 1.9750463807653873e-05, "epoch": 0.49201277955271566, "percentage": 16.45, "elapsed_time": "0:27:16", "remaining_time": "2:18:30"}
+{"current_steps": 78, "total_steps": 468, "loss": 0.55, "lr": 1.9733626275673e-05, "epoch": 0.4984025559105431, "percentage": 16.67, "elapsed_time": "0:27:37", "remaining_time": "2:18:06"}
+{"current_steps": 79, "total_steps": 468, "loss": 0.481, "lr": 1.9716246732560715e-05, "epoch": 0.5047923322683706, "percentage": 16.88, "elapsed_time": "0:28:01", "remaining_time": "2:17:58"}
+{"current_steps": 80, "total_steps": 468, "loss": 0.5076, "lr": 1.9698326146086446e-05, "epoch": 0.5111821086261981, "percentage": 17.09, "elapsed_time": "0:28:21", "remaining_time": "2:17:30"}
+{"current_steps": 81, "total_steps": 468, "loss": 0.5441, "lr": 1.967986551414728e-05, "epoch": 0.5175718849840255, "percentage": 17.31, "elapsed_time": "0:28:41", "remaining_time": "2:17:04"}
+{"current_steps": 82, "total_steps": 468, "loss": 0.5547, "lr": 1.9660865864712413e-05, "epoch": 0.5239616613418531, "percentage": 17.52, "elapsed_time": "0:28:59", "remaining_time": "2:16:30"}
+{"current_steps": 83, "total_steps": 468, "loss": 0.5214, "lr": 1.9641328255765916e-05, "epoch": 0.5303514376996805, "percentage": 17.74, "elapsed_time": "0:29:24", "remaining_time": "2:16:25"}
+{"current_steps": 84, "total_steps": 468, "loss": 0.4978, "lr": 1.96212537752478e-05, "epoch": 0.536741214057508, "percentage": 17.95, "elapsed_time": "0:29:43", "remaining_time": "2:15:54"}
+{"current_steps": 85, "total_steps": 468, "loss": 0.5498, "lr": 1.9600643540993453e-05, "epoch": 0.5431309904153354, "percentage": 18.16, "elapsed_time": "0:30:07", "remaining_time": "2:15:42"}
+{"current_steps": 86, "total_steps": 468, "loss": 0.5269, "lr": 1.9579498700671386e-05, "epoch": 0.549520766773163, "percentage": 18.38, "elapsed_time": "0:30:29", "remaining_time": "2:15:25"}
+{"current_steps": 87, "total_steps": 468, "loss": 0.5418, "lr": 1.9557820431719333e-05, "epoch": 0.5559105431309904, "percentage": 18.59, "elapsed_time": "0:30:47", "remaining_time": "2:14:52"}
+{"current_steps": 88, "total_steps": 468, "loss": 0.5113, "lr": 1.9535609941278676e-05, "epoch": 0.5623003194888179, "percentage": 18.8, "elapsed_time": "0:31:10", "remaining_time": "2:14:37"}
+{"current_steps": 89, "total_steps": 468, "loss": 0.5212, "lr": 1.9512868466127232e-05, "epoch": 0.5686900958466453, "percentage": 19.02, "elapsed_time": "0:31:30", "remaining_time": "2:14:08"}
+{"current_steps": 90, "total_steps": 468, "loss": 0.5216, "lr": 1.9489597272610377e-05, "epoch": 0.5750798722044729, "percentage": 19.23, "elapsed_time": "0:31:48", "remaining_time": "2:13:36"}
+{"current_steps": 91, "total_steps": 468, "loss": 0.5236, "lr": 1.9465797656570546e-05, "epoch": 0.5814696485623003, "percentage": 19.44, "elapsed_time": "0:32:11", "remaining_time": "2:13:20"}
+{"current_steps": 92, "total_steps": 468, "loss": 0.5028, "lr": 1.944147094327506e-05, "epoch": 0.5878594249201278, "percentage": 19.66, "elapsed_time": "0:32:30", "remaining_time": "2:12:49"}
+{"current_steps": 93, "total_steps": 468, "loss": 0.4934, "lr": 1.9416618487342333e-05, "epoch": 0.5942492012779552, "percentage": 19.87, "elapsed_time": "0:32:54", "remaining_time": "2:12:42"}
+{"current_steps": 94, "total_steps": 468, "loss": 0.5015, "lr": 1.9391241672666438e-05, "epoch": 0.6006389776357828, "percentage": 20.09, "elapsed_time": "0:33:17", "remaining_time": "2:12:27"}
+{"current_steps": 95, "total_steps": 468, "loss": 0.4852, "lr": 1.936534191234006e-05, "epoch": 0.6070287539936102, "percentage": 20.3, "elapsed_time": "0:33:37", "remaining_time": "2:12:01"}
+{"current_steps": 96, "total_steps": 468, "loss": 0.4993, "lr": 1.9338920648575798e-05, "epoch": 0.6134185303514377, "percentage": 20.51, "elapsed_time": "0:34:00", "remaining_time": "2:11:46"}
+{"current_steps": 97, "total_steps": 468, "loss": 0.5475, "lr": 1.9311979352625837e-05, "epoch": 0.6198083067092651, "percentage": 20.73, "elapsed_time": "0:34:20", "remaining_time": "2:11:21"}
+{"current_steps": 98, "total_steps": 468, "loss": 0.5269, "lr": 1.928451952470007e-05, "epoch": 0.6261980830670927, "percentage": 20.94, "elapsed_time": "0:34:45", "remaining_time": "2:11:12"}
+{"current_steps": 99, "total_steps": 468, "loss": 0.4965, "lr": 1.9256542693882505e-05, "epoch": 0.6325878594249201, "percentage": 21.15, "elapsed_time": "0:35:03", "remaining_time": "2:10:41"}
+{"current_steps": 100, "total_steps": 468, "loss": 0.505, "lr": 1.922805041804617e-05, "epoch": 0.6389776357827476, "percentage": 21.37, "elapsed_time": "0:35:26", "remaining_time": "2:10:25"}
+{"current_steps": 101, "total_steps": 468, "loss": 0.5301, "lr": 1.919904428376632e-05, "epoch": 0.645367412140575, "percentage": 21.58, "elapsed_time": "0:35:50", "remaining_time": "2:10:12"}
+{"current_steps": 102, "total_steps": 468, "loss": 0.5113, "lr": 1.916952590623212e-05, "epoch": 0.6517571884984026, "percentage": 21.79, "elapsed_time": "0:36:12", "remaining_time": "2:09:56"}
+{"current_steps": 103, "total_steps": 468, "loss": 0.5106, "lr": 1.9139496929156685e-05, "epoch": 0.65814696485623, "percentage": 22.01, "elapsed_time": "0:36:34", "remaining_time": "2:09:37"}
+{"current_steps": 104, "total_steps": 468, "loss": 0.5211, "lr": 1.910895902468557e-05, "epoch": 0.6645367412140575, "percentage": 22.22, "elapsed_time": "0:36:52", "remaining_time": "2:09:04"}
+{"current_steps": 105, "total_steps": 468, "loss": 0.5125, "lr": 1.907791389330363e-05, "epoch": 0.670926517571885, "percentage": 22.44, "elapsed_time": "0:37:08", "remaining_time": "2:08:25"}
+{"current_steps": 106, "total_steps": 468, "loss": 0.52, "lr": 1.904636326374036e-05, "epoch": 0.6773162939297125, "percentage": 22.65, "elapsed_time": "0:37:27", "remaining_time": "2:07:55"}
+{"current_steps": 107, "total_steps": 468, "loss": 0.5513, "lr": 1.9014308892873612e-05, "epoch": 0.6837060702875399, "percentage": 22.86, "elapsed_time": "0:37:49", "remaining_time": "2:07:36"}
+{"current_steps": 108, "total_steps": 468, "loss": 0.4891, "lr": 1.8981752565631767e-05, "epoch": 0.6900958466453674, "percentage": 23.08, "elapsed_time": "0:38:08", "remaining_time": "2:07:09"}
+{"current_steps": 109, "total_steps": 468, "loss": 0.5589, "lr": 1.8948696094894354e-05, "epoch": 0.6964856230031949, "percentage": 23.29, "elapsed_time": "0:38:28", "remaining_time": "2:06:41"}
+{"current_steps": 110, "total_steps": 468, "loss": 0.5306, "lr": 1.8915141321391083e-05, "epoch": 0.7028753993610224, "percentage": 23.5, "elapsed_time": "0:38:47", "remaining_time": "2:06:14"}
+{"current_steps": 111, "total_steps": 468, "loss": 0.5192, "lr": 1.8881090113599353e-05, "epoch": 0.7092651757188498, "percentage": 23.72, "elapsed_time": "0:39:09", "remaining_time": "2:05:56"}
+{"current_steps": 112, "total_steps": 468, "loss": 0.4906, "lr": 1.8846544367640218e-05, "epoch": 0.7156549520766773, "percentage": 23.93, "elapsed_time": "0:39:25", "remaining_time": "2:05:20"}
+{"current_steps": 113, "total_steps": 468, "loss": 0.5322, "lr": 1.881150600717279e-05, "epoch": 0.7220447284345048, "percentage": 24.15, "elapsed_time": "0:39:44", "remaining_time": "2:04:51"}
+{"current_steps": 114, "total_steps": 468, "loss": 0.5211, "lr": 1.8775976983287117e-05, "epoch": 0.7284345047923323, "percentage": 24.36, "elapsed_time": "0:40:06", "remaining_time": "2:04:34"}
+{"current_steps": 115, "total_steps": 468, "loss": 0.5252, "lr": 1.873995927439555e-05, "epoch": 0.7348242811501597, "percentage": 24.57, "elapsed_time": "0:40:28", "remaining_time": "2:04:14"}
+{"current_steps": 116, "total_steps": 468, "loss": 0.5349, "lr": 1.8703454886122568e-05, "epoch": 0.7412140575079872, "percentage": 24.79, "elapsed_time": "0:40:52", "remaining_time": "2:04:02"}
+{"current_steps": 117, "total_steps": 468, "loss": 0.5049, "lr": 1.86664658511931e-05, "epoch": 0.7476038338658147, "percentage": 25.0, "elapsed_time": "0:41:08", "remaining_time": "2:03:24"}
+{"current_steps": 118, "total_steps": 468, "loss": 0.4995, "lr": 1.862899422931934e-05, "epoch": 0.7539936102236422, "percentage": 25.21, "elapsed_time": "0:41:30", "remaining_time": "2:03:06"}
+{"current_steps": 119, "total_steps": 468, "loss": 0.5103, "lr": 1.859104210708604e-05, "epoch": 0.7603833865814696, "percentage": 25.43, "elapsed_time": "0:41:52", "remaining_time": "2:02:47"}
+{"current_steps": 120, "total_steps": 468, "loss": 0.4952, "lr": 1.855261159783432e-05, "epoch": 0.7667731629392971, "percentage": 25.64, "elapsed_time": "0:42:15", "remaining_time": "2:02:31"}
+{"current_steps": 121, "total_steps": 468, "loss": 0.5023, "lr": 1.8513704841543997e-05, "epoch": 0.7731629392971247, "percentage": 25.85, "elapsed_time": "0:42:37", "remaining_time": "2:02:15"}
+{"current_steps": 122, "total_steps": 468, "loss": 0.5487, "lr": 1.847432400471443e-05, "epoch": 0.7795527156549521, "percentage": 26.07, "elapsed_time": "0:43:01", "remaining_time": "2:02:00"}
+{"current_steps": 123, "total_steps": 468, "loss": 0.5061, "lr": 1.8434471280243854e-05, "epoch": 0.7859424920127795, "percentage": 26.28, "elapsed_time": "0:43:21", "remaining_time": "2:01:36"}
+{"current_steps": 124, "total_steps": 468, "loss": 0.5381, "lr": 1.8394148887307286e-05, "epoch": 0.792332268370607, "percentage": 26.5, "elapsed_time": "0:43:42", "remaining_time": "2:01:14"}
+{"current_steps": 125, "total_steps": 468, "loss": 0.5017, "lr": 1.8353359071232954e-05, "epoch": 0.7987220447284346, "percentage": 26.71, "elapsed_time": "0:44:05", "remaining_time": "2:00:59"}
+{"current_steps": 126, "total_steps": 468, "loss": 0.4935, "lr": 1.8312104103377266e-05, "epoch": 0.805111821086262, "percentage": 26.92, "elapsed_time": "0:44:24", "remaining_time": "2:00:32"}
+{"current_steps": 127, "total_steps": 468, "loss": 0.4877, "lr": 1.827038628099831e-05, "epoch": 0.8115015974440895, "percentage": 27.14, "elapsed_time": "0:44:44", "remaining_time": "2:00:09"}
+{"current_steps": 128, "total_steps": 468, "loss": 0.4971, "lr": 1.822820792712797e-05, "epoch": 0.8178913738019169, "percentage": 27.35, "elapsed_time": "0:45:06", "remaining_time": "1:59:49"}
+{"current_steps": 129, "total_steps": 468, "loss": 0.4835, "lr": 1.8185571390442542e-05, "epoch": 0.8242811501597445, "percentage": 27.56, "elapsed_time": "0:45:29", "remaining_time": "1:59:32"}
+{"current_steps": 130, "total_steps": 468, "loss": 0.5189, "lr": 1.8142479045131956e-05, "epoch": 0.8306709265175719, "percentage": 27.78, "elapsed_time": "0:45:49", "remaining_time": "1:59:09"}
+{"current_steps": 131, "total_steps": 468, "loss": 0.5229, "lr": 1.809893329076757e-05, "epoch": 0.8370607028753994, "percentage": 27.99, "elapsed_time": "0:46:10", "remaining_time": "1:58:46"}
+{"current_steps": 132, "total_steps": 468, "loss": 0.5328, "lr": 1.8054936552168548e-05, "epoch": 0.8434504792332268, "percentage": 28.21, "elapsed_time": "0:46:26", "remaining_time": "1:58:12"}
+{"current_steps": 133, "total_steps": 468, "loss": 0.4788, "lr": 1.801049127926686e-05, "epoch": 0.8498402555910544, "percentage": 28.42, "elapsed_time": "0:46:44", "remaining_time": "1:57:42"}
+{"current_steps": 134, "total_steps": 468, "loss": 0.4914, "lr": 1.7965599946970814e-05, "epoch": 0.8562300319488818, "percentage": 28.63, "elapsed_time": "0:47:03", "remaining_time": "1:57:18"}
+{"current_steps": 135, "total_steps": 468, "loss": 0.5175, "lr": 1.7920265055027285e-05, "epoch": 0.8626198083067093, "percentage": 28.85, "elapsed_time": "0:47:26", "remaining_time": "1:57:02"}
+{"current_steps": 136, "total_steps": 468, "loss": 0.5267, "lr": 1.7874489127882496e-05, "epoch": 0.8690095846645367, "percentage": 29.06, "elapsed_time": "0:47:50", "remaining_time": "1:56:46"}
+{"current_steps": 137, "total_steps": 468, "loss": 0.5226, "lr": 1.7828274714541445e-05, "epoch": 0.8753993610223643, "percentage": 29.27, "elapsed_time": "0:48:12", "remaining_time": "1:56:27"}
+{"current_steps": 138, "total_steps": 468, "loss": 0.5052, "lr": 1.7781624388425974e-05, "epoch": 0.8817891373801917, "percentage": 29.49, "elapsed_time": "0:48:33", "remaining_time": "1:56:06"}
+{"current_steps": 139, "total_steps": 468, "loss": 0.4775, "lr": 1.773454074723147e-05, "epoch": 0.8881789137380192, "percentage": 29.7, "elapsed_time": "0:48:55", "remaining_time": "1:55:48"}
+{"current_steps": 140, "total_steps": 468, "loss": 0.5383, "lr": 1.76870264127822e-05, "epoch": 0.8945686900958466, "percentage": 29.91, "elapsed_time": "0:49:19", "remaining_time": "1:55:32"}
+{"current_steps": 141, "total_steps": 468, "loss": 0.5107, "lr": 1.763908403088534e-05, "epoch": 0.9009584664536742, "percentage": 30.13, "elapsed_time": "0:49:41", "remaining_time": "1:55:15"}
+{"current_steps": 142, "total_steps": 468, "loss": 0.496, "lr": 1.759071627118362e-05, "epoch": 0.9073482428115016, "percentage": 30.34, "elapsed_time": "0:49:58", "remaining_time": "1:54:44"}
+{"current_steps": 143, "total_steps": 468, "loss": 0.5064, "lr": 1.754192582700668e-05, "epoch": 0.9137380191693291, "percentage": 30.56, "elapsed_time": "0:50:20", "remaining_time": "1:54:23"}
+{"current_steps": 144, "total_steps": 468, "loss": 0.5072, "lr": 1.7492715415221087e-05, "epoch": 0.9201277955271565, "percentage": 30.77, "elapsed_time": "0:50:38", "remaining_time": "1:53:57"}
+{"current_steps": 145, "total_steps": 468, "loss": 0.4866, "lr": 1.7443087776079068e-05, "epoch": 0.9265175718849841, "percentage": 30.98, "elapsed_time": "0:51:01", "remaining_time": "1:53:39"}
+{"current_steps": 146, "total_steps": 468, "loss": 0.4957, "lr": 1.739304567306588e-05, "epoch": 0.9329073482428115, "percentage": 31.2, "elapsed_time": "0:51:22", "remaining_time": "1:53:17"}
+{"current_steps": 147, "total_steps": 468, "loss": 0.5062, "lr": 1.7342591892745978e-05, "epoch": 0.939297124600639, "percentage": 31.41, "elapsed_time": "0:51:41", "remaining_time": "1:52:52"}
+{"current_steps": 148, "total_steps": 468, "loss": 0.5397, "lr": 1.72917292446078e-05, "epoch": 0.9456869009584664, "percentage": 31.62, "elapsed_time": "0:52:02", "remaining_time": "1:52:31"}
+{"current_steps": 149, "total_steps": 468, "loss": 0.502, "lr": 1.7240460560907345e-05, "epoch": 0.952076677316294, "percentage": 31.84, "elapsed_time": "0:52:20", "remaining_time": "1:52:02"}
+{"current_steps": 150, "total_steps": 468, "loss": 0.4981, "lr": 1.7188788696510477e-05, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:52:44", "remaining_time": "1:51:48"}
+{"current_steps": 151, "total_steps": 468, "loss": 0.4912, "lr": 1.7136716528733916e-05, "epoch": 0.9648562300319489, "percentage": 32.26, "elapsed_time": "0:53:01", "remaining_time": "1:51:18"}
+{"current_steps": 152, "total_steps": 468, "loss": 0.4716, "lr": 1.7084246957185036e-05, "epoch": 0.9712460063897763, "percentage": 32.48, "elapsed_time": "0:53:25", "remaining_time": "1:51:03"}
+{"current_steps": 153, "total_steps": 468, "loss": 0.4885, "lr": 1.703138290360041e-05, "epoch": 0.9776357827476039, "percentage": 32.69, "elapsed_time": "0:53:44", "remaining_time": "1:50:39"}
+{"current_steps": 154, "total_steps": 468, "loss": 0.5054, "lr": 1.6978127311683103e-05, "epoch": 0.9840255591054313, "percentage": 32.91, "elapsed_time": "0:54:01", "remaining_time": "1:50:08"}
+{"current_steps": 155, "total_steps": 468, "loss": 0.489, "lr": 1.6924483146938756e-05, "epoch": 0.9904153354632588, "percentage": 33.12, "elapsed_time": "0:54:20", "remaining_time": "1:49:44"}
+{"current_steps": 156, "total_steps": 468, "loss": 0.5253, "lr": 1.6870453396510456e-05, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:54:40", "remaining_time": "1:49:21"}
+{"current_steps": 157, "total_steps": 468, "loss": 0.7729, "lr": 1.681604106901239e-05, "epoch": 1.0031948881789137, "percentage": 33.55, "elapsed_time": "0:55:45", "remaining_time": "1:50:27"}
+{"current_steps": 158, "total_steps": 468, "loss": 0.4368, "lr": 1.676124919436233e-05, "epoch": 1.0095846645367412, "percentage": 33.76, "elapsed_time": "0:56:04", "remaining_time": "1:50:01"}
+{"current_steps": 159, "total_steps": 468, "loss": 0.4075, "lr": 1.6706080823612897e-05, "epoch": 1.0159744408945688, "percentage": 33.97, "elapsed_time": "0:56:27", "remaining_time": "1:49:43"}
+{"current_steps": 160, "total_steps": 468, "loss": 0.3875, "lr": 1.665053902878167e-05, "epoch": 1.0223642172523961, "percentage": 34.19, "elapsed_time": "0:56:48", "remaining_time": "1:49:20"}
+{"current_steps": 161, "total_steps": 468, "loss": 0.4692, "lr": 1.659462690268013e-05, "epoch": 1.0287539936102237, "percentage": 34.4, "elapsed_time": "0:57:08", "remaining_time": "1:48:57"}
+{"current_steps": 162, "total_steps": 468, "loss": 0.4089, "lr": 1.6538347558741424e-05, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:57:28", "remaining_time": "1:48:33"}
+{"current_steps": 163, "total_steps": 468, "loss": 0.442, "lr": 1.6481704130847013e-05, "epoch": 1.0415335463258786, "percentage": 34.83, "elapsed_time": "0:57:48", "remaining_time": "1:48:09"}
+{"current_steps": 164, "total_steps": 468, "loss": 0.4464, "lr": 1.642469977315214e-05, "epoch": 1.0479233226837061, "percentage": 35.04, "elapsed_time": "0:58:10", "remaining_time": "1:47:49"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095a6c15b083ad66679899baf98837f02d2d2dba6d901cc5412181f8c9bb2303
+size 7224